IBM: Granite 4.2 8B API Pricing
IBM: Granite 4.2 8B costs $0.060 per 1M input tokens and $0.250 per 1M output tokens (cache reads: $0.015). Context window: 131K. Prices verified 2026-10-21 · source
Alternatives to consider
71% cheaper with nearly identical quality (20.1 vs 11.1)
+30 quality points for 5% more
Cheapest ibm-granite model — 62% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
High adoption means battle-tested weights, more fine-tunes/quants, and faster bug fixes. View on HuggingFace →
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.060 | — |
| Cache read | $0.015 | −75% |
| Output | $0.250 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Higher effort = deeper thinking = more reasoning tokens billed as output.
What would IBM: Granite 4.2 8B cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $1.48 |
| Coding agent | 5,000 | 8,000 / 2,000 | $4.90 |
| RAG pipeline | 30,000 | 4,000 / 500 | $10.95 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $2.90 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About IBM: Granite 4.2 8B
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Compare IBM: Granite 4.2 8B with
- 4.2 8B vs OpenAI: GPT-5.6 Terra Pro
- 4.2 8B vs Anthropic: Claude Fable 5
- 4.2 8B vs Anthropic: Claude Opus 5
- 4.2 8B vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does IBM: Granite 4.2 8B cost?
IBM: Granite 4.2 8B costs $0.060 per 1M input tokens and $0.250 per 1M output tokens; cached input tokens cost $0.015 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
131K tokens, with up to 118K output tokens per response. That's roughly 164 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.015/1M, about 75% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
Mistral: Mistral Nemo saves about 74% on a typical workload with comparable quality.
Official resources
- IBM: Granite 4.2 8B on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Shred your current bill — paste a CSV and see if switching saves money.